3D Context-Aware Convolutional Neural Network for False Positive Reduction in Clustered Microcalcifications Detection

False positives (FPs) reduction is indispensable for clustered microcalcifications (MCs) detection in digital breast tomosynthesis (DBT), since there might be excessive false candidates in the detection stage. Considering that DBT volume has an anisotropic resolution, we proposed a novel 3D context-aware convolutional neural network (CNN) to reduce FPs, which consists of a 2D intra-slices feature extraction branch and a 3D inter-slice features fusion branch. In particular, 3D anisotropic convolutions were designed to learn representations from DBT volumes and inter-slice information fusion is only performed on the feature map level, which could avoid the influence of anisotropic resolution of DBT volume. The proposed method was evaluated on a large-scale Chinese women population of 877 cases with 1754 DBT volumes and compared with 8 related methods. Experimental results show that the proposed network achieved the best performance with an accuracy of 92.68% for FPs reduction with an AUC of 97.65%, and the FPs are 0.0512 per DBT volume at a sensitivity of 90%. This also proved that making full use of 3D contextual information of DBT volume can improve the performance of the classification algorithm.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yongyi Yang,et al.  Improving the accuracy in detection of clustered microcalcifications with a context-sensitive classification model. , 2016, Medical physics.

[3]  Berkman Sahiner,et al.  Computer aided detection of clusters of microcalcifications on full field digital mammograms. , 2006, Medical physics.

[4]  KathleenR. Brandt,et al.  Screening mammograms: interpretation with computer-aided detection--prospective evaluation. , 2006, Radiology.

[5]  Lubomir M. Hadjiiski,et al.  Deep-learning convolution neural network for computer-aided detection of microcalcifications in digital breast tomosynthesis , 2016, SPIE Medical Imaging.

[6]  Hao Chen,et al.  Automatic detection of cerebral microbleeds via deep learning based 3D feature representation , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[7]  Peerapon Vateekul,et al.  Deep multi-label 3D ConvNet for breast cancer diagnosis in DBT with inversion augmentation , 2018, International Conference on Digital Image Processing.

[8]  C. D'Orsi,et al.  Influence of computer-aided detection on performance of screening mammography. , 2007, The New England journal of medicine.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  M. Gromet.  Comparison of computer-aided detection to double reading of screening mammograms: review of 231,221 mammograms. , 2008, AJR. American journal of roentgenology.

[11]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Daguang Xu,et al.  3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes , 2017, MICCAI.

[13]  Lia Morra,et al.  Breast Cancer: Computer-aided Detection with Digital Breast Tomosynthesis. , 2015, Radiology.

[14]  R. Blanks,et al.  A comparison of cancer detection rates achieved by breast cancer screening programmes by number of readers, for one and two view mammography: results from the UK National Health Service breast screening programme , 1998, Journal of medical screening.

[15]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[16]  Frank W. Samuelson,et al.  Comparing image detection algorithms using resampling , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[17]  Nico Karssemeijer,et al.  Improving computer‐aided detection assistance in breast cancer screening by removal of obviously false‐positive findings , 2017, Medical physics.

[18]  Yin Yin,et al.  Transferring Learned Microcalcification Group Detection from 2D Mammography to 3D Digital Breast Tomosynthesis Using a Hierarchical Model and Scope-based Normalization Features , 2016, ArXiv.

[19]  Andrew P. Bradley,et al.  Automated Analysis of Unregistered Multi-View Mammograms With Deep Learning , 2017, IEEE Transactions on Medical Imaging.

[20]  Nico Karssemeijer,et al.  Effect of independent multiple reading of mammograms on detection performance , 2004, SPIE Medical Imaging.

[21]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  I. Sechopoulos.  A review of breast tomosynthesis. Part I. The image acquisition process. , 2013, Medical physics.

[23]  Ugur Halici,et al.  Ensemble of convolutional neural networks for classification of breast microcalcification from mammograms , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  Zhang Yi,et al.  Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification , 2020, IEEE Transactions on Medical Imaging.

[25]  Yongyi Yang,et al.  A context-sensitive deep learning approach for microcalcification detection in mammograms , 2018, Pattern Recognit..

[26]  Tao Mei,et al.  Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[27]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[28]  D. Kopans,et al.  Digital Breast Tomosynthesis: State of the Art. , 2015, Radiology.

[29]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Nikos Paragios,et al.  Context Aware 3D CNNs for Brain Tumor Segmentation , 2018, BrainLes@MICCAI.

[31]  Hongmin Cai,et al.  Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning , 2016, Scientific Reports.

[32]  Cheng Zhang,et al.  Multi‐domain features for reducing false positives in automated detection of clustered microcalcifications in digital breast tomosynthesis , 2019, Medical physics.

[33]  R M Nishikawa,et al.  Image feature analysis and computer-aided diagnosis in mammography: reduction of false-positive clustered microcalcifications using local edge-gradient analysis. , 1995, Medical physics.

[34]  Berkman Sahiner,et al.  Computer-aided detection of clustered microcalcifications in multiscale bilateral filtering regularized reconstructed digital breast tomosynthesis volume. , 2014, Medical physics.

[35]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..